Proc. SPIE. 6806, Human Vision and Electronic Imaging XIII
KEYWORDS: Image segmentation, Image processing algorithms and systems, Color image segmentation, Color image processing, Electrical engineering, Human vision and color perception, Electronic imaging, Image processing, RGB color model, Radiation oncology
We propose a novel algorithm for unsupervised segmentation of color images. The proposed approach utilizes a dynamic
color gradient thresholding scheme that guides the region growing process. Given a color image, a weighted vectorbased
color gradient map is generated. Seeds are identified and a dynamic threshold is then used to perform reliable
growing of regions on the weighted gradient map. Over-segmentation, if any, is addressed by a Similarity Measurebased
region merging stage to produce the final segmented image. Comparative results demonstrate the effectiveness of
this algorithm for color image segmentation.